Method and system for detecting drift in image streams

Abstract

Methods and systems disclosed herein may quantify a representation of a type of input an image analysis system should expect. The image analysis system may be trained on the type of input the image analysis system should expect using a first image stream. A first model of the type of input that the image analysis system should expect may be built from the first image stream. After the first model is built, a second image, or a second image stream, may be compared to the first model to determine a difference between the second image, or second image stream, and the first image stream. When the difference is greater than or equal to a threshold, a drift may be detected and steps may be taken to determine the cause of the drift.

What is claimed is: 
     
       1. A method comprising:
 building, by a first device, a first model based on a first stream, wherein the first model represents a first probability distribution of a first plurality of features appearing in the first stream; 
 building, by the first device, a second model based on a second stream, wherein the second model represents a second probability distribution of a second plurality of features appearing in the second stream; 
 comparing the second model to the first model to determine a difference between the second stream and the first stream; and 
 indicating that the second stream is significantly different from the first stream based on the difference being greater than or equal to a threshold, wherein significantly different indicates that the second stream is outside an accepted range of tolerance. 
 
     
     
       2. The method of  claim 1 , wherein building the first model further comprises:
 determining a first numeric representation of first data in the first stream; 
 determining a second numeric representation of second data in the first stream; 
 determining the first plurality of features by identifying one or more features that appear in both the first numeric representation and the second numeric representation; and 
 generating the first model based on how often each of the first plurality of features appear in both the first numeric representation and the second numeric representation. 
 
     
     
       3. The method of  claim 1 , comprising:
 notifying an administrator, via an application, that the second stream is significantly different from the first stream. 
 
     
     
       4. The method of  claim 1 , comprising:
 issuing, via an application, at least one command to an input source to correct a cause of the difference between the second stream and the first stream. 
 
     
     
       5. The method of  claim 1 , further comprising:
 receiving the first stream from an input source; and 
 receiving the second stream from the input source. 
 
     
     
       6. The method of  claim 5 , wherein the input source comprises one or more scanners associated with an automated teller machine. 
     
     
       7. The method of  claim 1 , wherein:
 the first stream comprises a first plurality of images obtained via an input source; and 
 the second stream comprises a second plurality of images obtained via the input source. 
 
     
     
       8. The method of  claim 1 , wherein the second stream being outside the accepted range of tolerance indicates a change between the first stream and the second stream. 
     
     
       9. A computing device comprising:
 one or more processors; and 
 memory storing instructions that, when executed by the one or more processors, cause the computing device to:
 build a first model based on a first stream, wherein the first model represents a first probability distribution of a first plurality of features appearing in the first stream; 
 build a second model based on a second stream, wherein the second model represents a second probability distribution of a second plurality of features appearing in the second stream; 
 compare the second model to the first model to determine a difference between the second stream and the first stream; and 
 indicate that the second stream is significantly different from the first stream when the difference is greater than or equal to a threshold, wherein significantly different indicates that the second stream is outside an accepted range of tolerance. 
 
 
     
     
       10. The computing device of  claim 9 , wherein the instructions, when executed by the one or more processors, cause the computing device to:
 determine a first numeric representation of first data in the first stream; 
 determine a second numeric representation of second data in the first stream; 
 determine the first plurality of features by identifying one or more features that appear in both the first numeric representation and the second numeric representation; and 
 generate the first model based on how often each of the first plurality of features appear in both the first numeric representation and the second numeric representation. 
 
     
     
       11. The computing device of  claim 9 , wherein the instructions, when executed by the one or more processors, cause the computing device to:
 notify an administrator, via an application, that the second stream is significantly different from the first stream. 
 
     
     
       12. The computing device of  claim 9 , wherein the instructions, when executed by the one or more processors, cause the computing device to:
 issue, via an application, at least one command to an input source to correct a cause of the difference between the second stream and the first stream. 
 
     
     
       13. The computing device of  claim 9 , further comprising:
 an interface configured to:
 receive the first stream from an input source; and 
 receive the second stream from the input source. 
 
 
     
     
       14. The computing device of  claim 13 , wherein the input source comprises one or more scanners associated with an automated teller machine. 
     
     
       15. The computing device of  claim 9 , wherein:
 the first stream comprises a first plurality of images obtained via an input source; and 
 the second stream comprises a second plurality of images obtained via the input source. 
 
     
     
       16. The computing device of  claim 9 , wherein the second stream being outside the accepted range of tolerance indicates a change between the first stream and the second stream. 
     
     
       17. A non-transitory computer-readable medium storing instructions that, when executed, cause a computing device to:
 build a first model based on a first stream, wherein the first model represents a first probability distribution of a first plurality of features appearing in the first stream; 
 build a second model based on a second stream, wherein the second model represents a second probability distribution of a second plurality of features appearing in the second stream; 
 compare the second model to the first model to determine a difference between the second stream and the first stream; and 
 indicate that the second stream is significantly different from the first stream when the difference is greater than or equal to a threshold, wherein significantly different indicates that the second stream is outside an accepted range of tolerance. 
 
     
     
       18. The non-transitory computer-readable medium of  claim 17 , wherein the instructions, when executed, cause the computing device to:
 determine a first numeric representation of first data in the first stream; 
 determine a second numeric representation of second data in the first stream; 
 determine the first plurality of features by identifying one or more features that appear in both the first numeric representation and the second numeric representation; and 
 generate the first model based on how often each of the first plurality of features appear in both the first numeric representation and the second numeric representation. 
 
     
     
       19. The non-transitory computer-readable medium of  claim 17 , wherein the instructions, when executed, cause the computing device to:
 notify an administrator, via an application, that the second stream is significantly different from the first stream. 
 
     
     
       20. The non-transitory computer-readable medium of  claim 17 , wherein the instructions, when executed, cause the computing device to:
 issue, via an application, at least one command to an input source to correct a cause of the difference between the second stream and the first stream. 
 
     
     
       21. The non-transitory computer-readable medium of  claim 17 , the instructions, when executed, cause the computing device to:
 receive the first stream from an input source; and 
 receive the second stream from the input source. 
 
     
     
       22. The non-transitory computer-readable medium of  claim 21 , wherein the input source comprises one or more scanners associated with an automated teller machine. 
     
     
       23. The non-transitory computer-readable medium of  claim 17 , wherein:
 the first stream comprises a first plurality of images obtained via an input source; and 
 the second stream comprises a second plurality of images obtained via the input source. 
 
     
     
       24. The non-transitory computer-readable medium of  claim 17 , wherein the second stream being outside the accepted range of tolerance indicates a change between the first stream and the second stream.